Daily Dose of Data Science | Avi Chawla | Substack·1y10 MCP, AI Agents, and RAG projects for AI Engineers
Explore 10 AI-focused projects including building an MCP-powered Agentic RAG, a multi-agent book writer, and a RAG system that understands audio content. Learn how to build and fine-tune AI models like DeepSeek-R1 and create applications using open-source tools like Llama 4 and Colpali.
freeCodeCamp·1yEssential Machine Learning and AI Concepts Animated
Learn essential machine learning and AI concepts in an easy and visual way with this course from Vladimir of Touring Time Machine. Key topics covered include variance, unsupervised learning, time series analysis, transfer learning, gradient descent, logistic regression, and neural networks, among others. The focus is on simplifying complex ideas with animations, avoiding jargon, and making learning accessible and engaging.
freeCodeCamp·1yCode DeepSeek V3 From Scratch in Python - Full Course
This post covers a comprehensive guide to understanding and implementing DeepSeek V3, a cutting-edge deep learning model. It includes step-by-step instructions and theoretical insights. DeepSeek V3 is noted for its advanced multi-head latent attention mechanism, rotary positional embeddings, and efficient matrix multiplications across GPUs. The guide offers explanations of key concepts and includes coding instructions to help readers implement the model from scratch.
ML CMU·1yMachine Learning Blog | ML@CMU | Carnegie Mellon University
Copilot Arena is a Visual Studio Code extension designed to evaluate large language models (LLMs) in real-world settings by collecting developer preferences during their actual workflow. The platform has gained over 11,000 users and supports numerous code completions and completion battles. It has shown insights into user preferences and how different models perform on various tasks. The evaluation highlights the importance of human feedback for performance metrics, contrasting with static benchmarks. Extensions to include more nuanced feedback mechanisms are encouraged.
Daily Dose of Data Science | Avi Chawla | Substack·1y[Hands-on] Build Your Reasoning LLM
Reinforcement fine-tuning (RFT) allows the transformation of open-source LLMs into advanced reasoning models without needing labeled data. The post guides using Predibase for RFT to enhance Qwen-2.5:7b. It contrasts RFT with supervised fine-tuning (SFT), highlights the steps involved in setting up and training using the Countdown dataset, and explains the reward functions used for model evaluation.